Browsing by Subject "CNN"

Sort by: Order: Results:

Now showing items 1-4 of 4

  • Automatic program generation for convolutional neural networks on resource constrained devices 

    Keane, Cormac David (Trinity College Dublin. School of Computer Science & Statistics. Discipline of Computer Science, 2022)
    Convolutional Neural Networks (CNNs) are both arithmetically and memory intensive when performing inference. This is a problem when executing CNNs on resource constrained machines, such as small embedded devices. This ...

  • Deep Convolutional Neural Networks for estimating lens distortion parameters 

    Smolic, Aljosa; Lutz, Sebastian; Davey, Mark (2019)
    In this paper we present a convolutional neural network (CNN) to predict multiple lens distortion parameters from a single input image. Unlike other methods, our network is suitable to create high resolution output as ...

  • DeepStereoBrush: Interactive Depth Map Creation 

    Smolic, Aljosa (2018)
    In this paper, we introduce a novel interactive depth map creation approach for image sequences which uses depth-scribbles as input at user-defined keyframes. These scribbled depth values are then propagated within these ...

  • Endogenous and Exogenous Factors Shaping Visual Development in Early Infancy 

    Kravchenko, Anna (Trinity College Dublin. School of Psychology. Discipline of Psychology, 2023)
    The human mind is capable of forming elaborate concepts and models of the world and manipulating them so that it can adapt to complex, rapidly changing environments. In contrast with that, machine learning methods and ...